Add model pricing file (#1483)

embedchain/embedchain/config/llm/base.py

@@ -234,7 +234,7 @@ class BaseLlmConfig(BaseConfig):
         self.api_version = api_version
 
         if token_usage:
-            f = open("model_prices_and_context_window.json")
+            f = open("config/model_prices_and_context_window.json")
             self.model_pricing_map = json.load(f)
 
         if isinstance(prompt, str):

embedchain/embedchain/config/model_prices_and_context_window.json

@@ -0,0 +1,803 @@
+{
+    "openai/gpt-4": {
+        "max_tokens": 4096, 
+        "max_input_tokens": 8192,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.00003,
+        "output_cost_per_token": 0.00006
+    },
+    "openai/gpt-4o": {
+        "max_tokens": 4096,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.000005,
+        "output_cost_per_token": 0.000015
+    },
+    "openai/gpt-4o-2024-05-13": {
+        "max_tokens": 4096,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.000005,
+        "output_cost_per_token": 0.000015
+    },
+    "openai/gpt-4-turbo-preview": {
+        "max_tokens": 4096,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.00001,
+        "output_cost_per_token": 0.00003
+    },
+    "openai/gpt-4-0314": {
+        "max_tokens": 4096,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.00003,
+        "output_cost_per_token": 0.00006
+    },
+    "openai/gpt-4-0613": {
+        "max_tokens": 4096,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.00003,
+        "output_cost_per_token": 0.00006
+    },
+    "openai/gpt-4-32k": {
+        "max_tokens": 4096,
+        "max_input_tokens": 32768,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.00006,
+        "output_cost_per_token": 0.00012
+    },
+    "openai/gpt-4-32k-0314": {
+        "max_tokens": 4096,
+        "max_input_tokens": 32768,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.00006,
+        "output_cost_per_token": 0.00012
+    },
+    "openai/gpt-4-32k-0613": {
+        "max_tokens": 4096,
+        "max_input_tokens": 32768,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.00006,
+        "output_cost_per_token": 0.00012
+    },
+    "openai/gpt-4-turbo": {
+        "max_tokens": 4096,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.00001,
+        "output_cost_per_token": 0.00003
+    },
+    "openai/gpt-4-turbo-2024-04-09": {
+        "max_tokens": 4096,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.00001,
+        "output_cost_per_token": 0.00003
+    },
+    "openai/gpt-4-1106-preview": {
+        "max_tokens": 4096,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.00001,
+        "output_cost_per_token": 0.00003
+    },
+    "openai/gpt-4-0125-preview": {
+        "max_tokens": 4096,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.00001,
+        "output_cost_per_token": 0.00003
+    },
+    "openai/gpt-3.5-turbo": {
+        "max_tokens": 4097,
+        "max_input_tokens": 16385,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.0000015,
+        "output_cost_per_token": 0.000002
+    },
+    "openai/gpt-3.5-turbo-0301": {
+        "max_tokens": 4097,
+        "max_input_tokens": 4097,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.0000015,
+        "output_cost_per_token": 0.000002
+    },
+    "openai/gpt-3.5-turbo-0613": {
+        "input_cost_per_token": 0.0000015,
+        "output_cost_per_token": 0.000002
+    },
+    "openai/gpt-3.5-turbo-1106": {
+        "max_tokens": 16385,
+        "max_input_tokens": 16385,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.0000010,
+        "output_cost_per_token": 0.0000020
+    },
+    "openai/gpt-3.5-turbo-0125": {
+        "max_tokens": 16385,
+        "max_input_tokens": 16385,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.0000005,
+        "output_cost_per_token": 0.0000015
+    },
+    "openai/gpt-3.5-turbo-16k": {
+        "max_tokens": 16385,
+        "max_input_tokens": 16385,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.000003,
+        "output_cost_per_token": 0.000004
+    },
+    "openai/gpt-3.5-turbo-16k-0613": {
+        "max_tokens": 16385,
+        "max_input_tokens": 16385,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.000003,
+        "output_cost_per_token": 0.000004
+    },
+    "openai/text-embedding-3-large": {
+        "max_tokens": 8191,
+        "max_input_tokens": 8191,
+        "output_vector_size": 3072,
+        "input_cost_per_token": 0.00000013,
+        "output_cost_per_token": 0.000000
+    },
+    "openai/text-embedding-3-small": {
+        "max_tokens": 8191,
+        "max_input_tokens": 8191,
+        "output_vector_size": 1536,
+        "input_cost_per_token": 0.00000002,
+        "output_cost_per_token": 0.000000
+    },
+    "openai/text-embedding-ada-002": {
+        "max_tokens": 8191,
+        "max_input_tokens": 8191,
+        "output_vector_size": 1536, 
+        "input_cost_per_token": 0.0000001,
+        "output_cost_per_token": 0.000000
+    },
+    "openai/text-embedding-ada-002-v2": {
+        "max_tokens": 8191,
+        "max_input_tokens": 8191,
+        "input_cost_per_token": 0.0000001,
+        "output_cost_per_token": 0.000000
+    },
+    "openai/babbage-002": {
+        "max_tokens": 16384,
+        "max_input_tokens": 16384,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.0000004,
+        "output_cost_per_token": 0.0000004
+    },
+    "openai/davinci-002": {
+        "max_tokens": 16384,
+        "max_input_tokens": 16384,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.000002,
+        "output_cost_per_token": 0.000002
+    },    
+    "openai/gpt-3.5-turbo-instruct": {
+        "max_tokens": 4096,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.0000015,
+        "output_cost_per_token": 0.000002
+    },
+    "openai/gpt-3.5-turbo-instruct-0914": {
+        "max_tokens": 4097,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 4097,
+        "input_cost_per_token": 0.0000015,
+        "output_cost_per_token": 0.000002
+    },
+    "azure/gpt-4o": {
+        "max_tokens": 4096,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.000005,
+        "output_cost_per_token": 0.000015
+    },
+    "azure/gpt-4-turbo-2024-04-09": {
+        "max_tokens": 4096,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.00001,
+        "output_cost_per_token": 0.00003
+    },
+    "azure/gpt-4-0125-preview": {
+        "max_tokens": 4096,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.00001,
+        "output_cost_per_token": 0.00003
+    },
+    "azure/gpt-4-1106-preview": {
+        "max_tokens": 4096,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.00001,
+        "output_cost_per_token": 0.00003
+    },
+    "azure/gpt-4-0613": {
+        "max_tokens": 4096,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.00003,
+        "output_cost_per_token": 0.00006
+    },
+    "azure/gpt-4-32k-0613": {
+        "max_tokens": 4096,
+        "max_input_tokens": 32768,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.00006,
+        "output_cost_per_token": 0.00012
+    },
+    "azure/gpt-4-32k": {
+        "max_tokens": 4096,
+        "max_input_tokens": 32768,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.00006,
+        "output_cost_per_token": 0.00012
+    },
+    "azure/gpt-4": {
+        "max_tokens": 4096,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.00003,
+        "output_cost_per_token": 0.00006
+    },
+    "azure/gpt-4-turbo": {
+        "max_tokens": 4096,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.00001,
+        "output_cost_per_token": 0.00003
+    },
+    "azure/gpt-4-turbo-vision-preview": {
+        "max_tokens": 4096,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.00001,
+        "output_cost_per_token": 0.00003
+    },
+    "azure/gpt-3.5-turbo-16k-0613": {
+        "max_tokens": 4096,
+        "max_input_tokens": 16385,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.000003,
+        "output_cost_per_token": 0.000004
+    },
+    "azure/gpt-3.5-turbo-1106": {
+        "max_tokens": 4096,
+        "max_input_tokens": 16384,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.0000015,
+        "output_cost_per_token": 0.000002
+    },
+    "azure/gpt-3.5-turbo-0125": {
+        "max_tokens": 4096,
+        "max_input_tokens": 16384,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.0000005,
+        "output_cost_per_token": 0.0000015
+    },
+    "azure/gpt-3.5-turbo-16k": {
+        "max_tokens": 4096,
+        "max_input_tokens": 16385,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.000003,
+        "output_cost_per_token": 0.000004
+    },
+    "azure/gpt-3.5-turbo": {
+        "max_tokens": 4096,
+        "max_input_tokens": 4097,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.0000005,
+        "output_cost_per_token": 0.0000015
+    },
+    "azure/gpt-3.5-turbo-instruct-0914": {
+        "max_tokens": 4097,
+        "max_input_tokens": 4097,
+        "input_cost_per_token": 0.0000015,
+        "output_cost_per_token": 0.000002
+    },
+    "azure/gpt-3.5-turbo-instruct": {
+        "max_tokens": 4097,
+        "max_input_tokens": 4097,
+        "input_cost_per_token": 0.0000015,
+        "output_cost_per_token": 0.000002
+    },
+    "azure/text-embedding-ada-002": {
+        "max_tokens": 8191,
+        "max_input_tokens": 8191,
+        "input_cost_per_token": 0.0000001,
+        "output_cost_per_token": 0.000000
+    },
+    "azure/text-embedding-3-large": {
+        "max_tokens": 8191,
+        "max_input_tokens": 8191,
+        "input_cost_per_token": 0.00000013,
+        "output_cost_per_token": 0.000000
+    },
+    "azure/text-embedding-3-small": {
+        "max_tokens": 8191,
+        "max_input_tokens": 8191,
+        "input_cost_per_token": 0.00000002,
+        "output_cost_per_token": 0.000000
+    }, 
+    "mistralai/mistral-tiny": {
+        "max_tokens": 8191,
+        "max_input_tokens": 32000,
+        "max_output_tokens": 8191,
+        "input_cost_per_token": 0.00000025,
+        "output_cost_per_token": 0.00000025
+    },
+    "mistralai/mistral-small": {
+        "max_tokens": 8191,
+        "max_input_tokens": 32000,
+        "max_output_tokens": 8191,
+        "input_cost_per_token": 0.000001,
+        "output_cost_per_token": 0.000003
+    },
+    "mistralai/mistral-small-latest": {
+        "max_tokens": 8191,
+        "max_input_tokens": 32000,
+        "max_output_tokens": 8191,
+        "input_cost_per_token": 0.000001,
+        "output_cost_per_token": 0.000003
+    },
+    "mistralai/mistral-medium": {
+        "max_tokens": 8191,
+        "max_input_tokens": 32000,
+        "max_output_tokens": 8191,
+        "input_cost_per_token": 0.0000027,
+        "output_cost_per_token": 0.0000081
+    },
+    "mistralai/mistral-medium-latest": {
+        "max_tokens": 8191,
+        "max_input_tokens": 32000,
+        "max_output_tokens": 8191,
+        "input_cost_per_token": 0.0000027,
+        "output_cost_per_token": 0.0000081
+    },
+    "mistralai/mistral-medium-2312": {
+        "max_tokens": 8191,
+        "max_input_tokens": 32000,
+        "max_output_tokens": 8191,
+        "input_cost_per_token": 0.0000027,
+        "output_cost_per_token": 0.0000081
+    },
+    "mistralai/mistral-large-latest": {
+        "max_tokens": 8191,
+        "max_input_tokens": 32000,
+        "max_output_tokens": 8191,
+        "input_cost_per_token": 0.000004,
+        "output_cost_per_token": 0.000012
+    },
+    "mistralai/mistral-large-2402": {
+        "max_tokens": 8191,
+        "max_input_tokens": 32000,
+        "max_output_tokens": 8191,
+        "input_cost_per_token": 0.000004,
+        "output_cost_per_token": 0.000012
+    },
+    "mistralai/open-mistral-7b": {
+        "max_tokens": 8191,
+        "max_input_tokens": 32000,
+        "max_output_tokens": 8191,
+        "input_cost_per_token": 0.00000025,
+        "output_cost_per_token": 0.00000025
+    },
+    "mistralai/open-mixtral-8x7b": {
+        "max_tokens": 8191,
+        "max_input_tokens": 32000,
+        "max_output_tokens": 8191,
+        "input_cost_per_token": 0.0000007,
+        "output_cost_per_token": 0.0000007
+    },
+    "mistralai/open-mixtral-8x22b": {
+        "max_tokens": 8191,
+        "max_input_tokens": 64000,
+        "max_output_tokens": 8191,
+        "input_cost_per_token": 0.000002,
+        "output_cost_per_token": 0.000006
+    },
+    "mistralai/codestral-latest": {
+        "max_tokens": 8191,
+        "max_input_tokens": 32000,
+        "max_output_tokens": 8191,
+        "input_cost_per_token": 0.000001,
+        "output_cost_per_token": 0.000003
+    },
+    "mistralai/codestral-2405": {
+        "max_tokens": 8191,
+        "max_input_tokens": 32000,
+        "max_output_tokens": 8191,
+        "input_cost_per_token": 0.000001,
+        "output_cost_per_token": 0.000003
+    },
+    "mistralai/mistral-embed": {
+        "max_tokens": 8192,
+        "max_input_tokens": 8192,
+        "input_cost_per_token": 0.0000001,
+        "output_cost_per_token": 0.0
+    },
+    "groq/llama2-70b-4096": {
+        "max_tokens": 4096,
+        "max_input_tokens": 4096,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.00000070,
+        "output_cost_per_token": 0.00000080
+    },
+    "groq/llama3-8b-8192": {
+        "max_tokens": 8192,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 0.00000010,
+        "output_cost_per_token": 0.00000010
+    },
+    "groq/llama3-70b-8192": {
+        "max_tokens": 8192,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 0.00000064,
+        "output_cost_per_token": 0.00000080
+    },
+    "groq/mixtral-8x7b-32768": {
+        "max_tokens": 32768,
+        "max_input_tokens": 32768,
+        "max_output_tokens": 32768,
+        "input_cost_per_token": 0.00000027,
+        "output_cost_per_token": 0.00000027
+    },
+    "groq/gemma-7b-it": {
+        "max_tokens": 8192,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 0.00000010,
+        "output_cost_per_token": 0.00000010
+    },
+    "anthropic/claude-instant-1": {
+        "max_tokens": 8191,
+        "max_input_tokens": 100000,
+        "max_output_tokens": 8191,
+        "input_cost_per_token": 0.00000163,
+        "output_cost_per_token": 0.00000551
+    },
+    "anthropic/claude-instant-1.2": {
+        "max_tokens": 8191,
+        "max_input_tokens": 100000,
+        "max_output_tokens": 8191,
+        "input_cost_per_token": 0.000000163,
+        "output_cost_per_token": 0.000000551
+    },
+    "anthropic/claude-2": {
+        "max_tokens": 8191,
+        "max_input_tokens": 100000,
+        "max_output_tokens": 8191,
+        "input_cost_per_token": 0.000008,
+        "output_cost_per_token": 0.000024
+    },
+    "anthropic/claude-2.1": {
+        "max_tokens": 8191,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 8191,
+        "input_cost_per_token": 0.000008,
+        "output_cost_per_token": 0.000024
+    },
+    "anthropic/claude-3-haiku-20240307": {
+        "max_tokens": 4096,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.00000025,
+        "output_cost_per_token": 0.00000125
+    },
+    "anthropic/claude-3-opus-20240229": {
+        "max_tokens": 4096,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.000015,
+        "output_cost_per_token": 0.000075
+    },
+    "anthropic/claude-3-sonnet-20240229": {
+        "max_tokens": 4096,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.000003,
+        "output_cost_per_token": 0.000015
+    },
+    "vertexai/chat-bison": {
+        "max_tokens": 4096,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.000000125,
+        "output_cost_per_token": 0.000000125
+    },
+    "vertexai/chat-bison@001": {
+        "max_tokens": 4096,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.000000125,
+        "output_cost_per_token": 0.000000125
+    },
+    "vertexai/chat-bison@002": {
+        "max_tokens": 4096,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.000000125,
+        "output_cost_per_token": 0.000000125
+    },
+    "vertexai/chat-bison-32k": {
+        "max_tokens": 8192,
+        "max_input_tokens": 32000,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 0.000000125,
+        "output_cost_per_token": 0.000000125
+    },
+    "vertexai/code-bison": {
+        "max_tokens": 1024,
+        "max_input_tokens": 6144,
+        "max_output_tokens": 1024,
+        "input_cost_per_token": 0.000000125,
+        "output_cost_per_token": 0.000000125
+    },
+    "vertexai/code-bison@001": {
+        "max_tokens": 1024,
+        "max_input_tokens": 6144,
+        "max_output_tokens": 1024,
+        "input_cost_per_token": 0.000000125,
+        "output_cost_per_token": 0.000000125
+    },
+    "vertexai/code-gecko@001": {
+        "max_tokens": 64,
+        "max_input_tokens": 2048,
+        "max_output_tokens": 64,
+        "input_cost_per_token": 0.000000125,
+        "output_cost_per_token": 0.000000125
+    },
+    "vertexai/code-gecko@002": {
+        "max_tokens": 64,
+        "max_input_tokens": 2048,
+        "max_output_tokens": 64,
+        "input_cost_per_token": 0.000000125,
+        "output_cost_per_token": 0.000000125
+    },
+    "vertexai/code-gecko": {
+        "max_tokens": 64,
+        "max_input_tokens": 2048,
+        "max_output_tokens": 64,
+        "input_cost_per_token": 0.000000125,
+        "output_cost_per_token": 0.000000125
+    },
+    "vertexai/codechat-bison": {
+        "max_tokens": 1024,
+        "max_input_tokens": 6144,
+        "max_output_tokens": 1024,
+        "input_cost_per_token": 0.000000125,
+        "output_cost_per_token": 0.000000125
+    },
+    "vertexai/codechat-bison@001": {
+        "max_tokens": 1024,
+        "max_input_tokens": 6144,
+        "max_output_tokens": 1024,
+        "input_cost_per_token": 0.000000125,
+        "output_cost_per_token": 0.000000125
+    },
+    "vertexai/codechat-bison-32k": {
+        "max_tokens": 8192,
+        "max_input_tokens": 32000,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 0.000000125,
+        "output_cost_per_token": 0.000000125
+    },
+    "vertexai/gemini-pro": {
+        "max_tokens": 8192,
+        "max_input_tokens": 32760,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 0.00000025, 
+        "output_cost_per_token": 0.0000005
+    },
+    "vertexai/gemini-1.0-pro": { 
+        "max_tokens": 8192,
+        "max_input_tokens": 32760,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 0.00000025, 
+        "output_cost_per_token": 0.0000005
+    },
+    "vertexai/gemini-1.0-pro-001": { 
+        "max_tokens": 8192,
+        "max_input_tokens": 32760,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 0.00000025, 
+        "output_cost_per_token": 0.0000005
+    },
+    "vertexai/gemini-1.0-pro-002": { 
+        "max_tokens": 8192,
+        "max_input_tokens": 32760,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 0.00000025, 
+        "output_cost_per_token": 0.0000005
+    },
+    "vertexai/gemini-1.5-pro": { 
+        "max_tokens": 8192,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 0.000000625, 
+        "output_cost_per_token": 0.000001875
+    },
+    "vertexai/gemini-1.5-flash-001": {
+        "max_tokens": 8192,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 0, 
+        "output_cost_per_token": 0
+    },
+    "vertexai/gemini-1.5-flash-preview-0514": {
+        "max_tokens": 8192,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 0, 
+        "output_cost_per_token": 0
+    },
+    "vertexai/gemini-1.5-pro-001": { 
+        "max_tokens": 8192,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 0.000000625, 
+        "output_cost_per_token": 0.000001875
+    },
+    "vertexai/gemini-1.5-pro-preview-0514": { 
+        "max_tokens": 8192,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 0.000000625, 
+        "output_cost_per_token": 0.000001875
+    },
+    "vertexai/gemini-1.5-pro-preview-0215": { 
+        "max_tokens": 8192,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 0.000000625, 
+        "output_cost_per_token": 0.000001875
+    },
+    "vertexai/gemini-1.5-pro-preview-0409": {
+        "max_tokens": 8192,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 0.000000625, 
+        "output_cost_per_token": 0.000001875
+    },
+    "vertexai/gemini-experimental": {
+        "max_tokens": 8192,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 0,
+        "output_cost_per_token": 0
+    },
+    "vertexai/gemini-pro-vision": {
+        "max_tokens": 2048,
+        "max_input_tokens": 16384,
+        "max_output_tokens": 2048,
+        "max_images_per_prompt": 16,
+        "max_videos_per_prompt": 1,
+        "max_video_length": 2,
+        "input_cost_per_token": 0.00000025, 
+        "output_cost_per_token": 0.0000005
+    },
+    "vertexai/gemini-1.0-pro-vision": {
+        "max_tokens": 2048,
+        "max_input_tokens": 16384,
+        "max_output_tokens": 2048,
+        "max_images_per_prompt": 16,
+        "max_videos_per_prompt": 1,
+        "max_video_length": 2,
+        "input_cost_per_token": 0.00000025, 
+        "output_cost_per_token": 0.0000005
+    },
+    "vertexai/gemini-1.0-pro-vision-001": {
+        "max_tokens": 2048,
+        "max_input_tokens": 16384,
+        "max_output_tokens": 2048,
+        "max_images_per_prompt": 16,
+        "max_videos_per_prompt": 1,
+        "max_video_length": 2,
+        "input_cost_per_token": 0.00000025, 
+        "output_cost_per_token": 0.0000005
+    },
+    "vertexai/claude-3-sonnet@20240229": {
+        "max_tokens": 4096,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.000003,
+        "output_cost_per_token": 0.000015
+    },
+    "vertexai/claude-3-haiku@20240307": {
+        "max_tokens": 4096, 
+        "max_input_tokens": 200000,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.00000025,
+        "output_cost_per_token": 0.00000125
+    },
+    "vertexai/claude-3-opus@20240229": {
+        "max_tokens": 4096,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.000015,
+        "output_cost_per_token": 0.000075
+    },
+    "cohere/command-r": {
+        "max_tokens": 4096, 
+        "max_input_tokens": 128000,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.00000050,
+        "output_cost_per_token": 0.0000015
+    },
+    "cohere/command-light": {
+        "max_tokens": 4096, 
+        "max_input_tokens": 4096,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.000015,
+        "output_cost_per_token": 0.000015
+    },
+    "cohere/command-r-plus": {
+        "max_tokens": 4096, 
+        "max_input_tokens": 128000,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.000003,
+        "output_cost_per_token": 0.000015
+    },
+    "cohere/command-nightly": {
+        "max_tokens": 4096, 
+        "max_input_tokens": 4096,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.000015,
+        "output_cost_per_token": 0.000015
+    },
+     "cohere/command": {
+        "max_tokens": 4096, 
+        "max_input_tokens": 4096,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.000015,
+        "output_cost_per_token": 0.000015
+    },
+     "cohere/command-medium-beta": {
+        "max_tokens": 4096, 
+        "max_input_tokens": 4096,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.000015,
+        "output_cost_per_token": 0.000015
+    },
+     "cohere/command-xlarge-beta": {
+        "max_tokens": 4096, 
+        "max_input_tokens": 4096,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.000015,
+        "output_cost_per_token": 0.000015
+    },
+    "together/together-ai-up-to-3b": {
+        "input_cost_per_token": 0.0000001,
+        "output_cost_per_token": 0.0000001
+    },
+    "together/together-ai-3.1b-7b": {
+        "input_cost_per_token": 0.0000002,
+        "output_cost_per_token": 0.0000002
+    },
+    "together/together-ai-7.1b-20b": {
+        "max_tokens": 1000,
+        "input_cost_per_token": 0.0000004,
+        "output_cost_per_token": 0.0000004
+    },
+    "together/together-ai-20.1b-40b": {
+        "input_cost_per_token": 0.0000008,
+        "output_cost_per_token": 0.0000008
+    },
+    "together/together-ai-40.1b-70b": {
+        "input_cost_per_token": 0.0000009,
+        "output_cost_per_token": 0.0000009
+    },
+    "together/mistralai/Mixtral-8x7B-Instruct-v0.1": {
+        "input_cost_per_token": 0.0000006,
+        "output_cost_per_token": 0.0000006
+    }
+}